A neural network model with self-organizing pulse-coupled oscillator

We consider a two layered neural network in which the second layer is compo sed of simple pulse-coupled neuronal oscillators connected by excitatory an d inhibitory lateral interaction weights. For storing information a self-or ganizing learning algorithm with respect to the amplitude of the neuronal o scillators is introduced. The dynamical behavior and the retrieval ability of information of this model are analyzed. Computer simulation shows that t he learning can enhance the coherent characteristic of the neuronal activit ies and the dynamical behaviors of this model in pattern recognition are si milar to the dynamical process in biological neural system and perform info rmation retrieval property to stored patterns.